# Research Papers — 2025-11 · bundle page 105 of 197 > Full-text markdown of papers #5201–5250 of 9830 published in 2025-11, newest first. AI-readable mirrors of the full 9830-paper 2025-11 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2025-11/page/105 [← Previous bundle](https://aipod.dev/papers/archive/2025-11/page/104.md) [Next bundle →](https://aipod.dev/papers/archive/2025-11/page/106.md) ### MMRINet: Efficient Mamba-Based Segmentation with Dual-Path Refinement for Low-Resource MRI Analysis Authors: Abdelrahman Elsayed, Ahmed Jaheen, Mohammad Yaqub Published: 2025-11-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.12193v2 Automated brain tumor segmentation in multi-parametric MRI remains a critical yet underserved challenge in resource-constrained clinical settings, where deep 3D networks requiring high-end GPUs are not viable. This is particularly acute across sub-Saharan Africa (SSA), where low-field scanners, heterogeneous patient demographics, and severe data scarcity compound the difficulty of applying standard deep learning pipelines. We present MMRINet, a lightweight segmentation architecture purpose-built for these constraints. At its core, MMRINet replaces quadratic-complexity self-attention with linear-complexity Mamba state-space models, enabling efficient long-range volumetric context modeling without the computational overhead of Transformer-based approaches. We combine two lightweight refinement components:Dual-Path Feature Refinement (DPFR), which extracts complementary detail and contextual representations to improve feature diversity under limited data, and Progressive Feature Aggregation (PFA), which hierarchically fuses multi-scale decoder outputs for sharper segmentation boundaries. Evaluated on the BraTS-Lighthouse SSA 2025 challenge dataset, comprising 3D MRI scans from Nigerian clinical sites, MMRINet achieves an average Dice score of 0.752 and an average HD95 of 12.23 mm with only ~2.5M parameters, outperforming all evaluated baselines, including UNETR, Swin-UNETR, SegMamba, and SegResNet3D. These results indicate that strong validation-set segmentation performance can be achieved with substantially reduced computation, offering a practical step toward AI-assisted neuro-oncology in low-resource clinical environments. Our GitHub repository can be accessed here: BioMedIA-MBZUAI/MMRINet. --- ### Evaluation of Multi- and Single-objective Learning Algorithms for Imbalanced Data Authors: Szymon Wojciechowski, Michał Woźniak Published: 2025-11-15 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.12191v1 Many machine learning tasks aim to find models that work well not for a single, but for a group of criteria, often opposing ones. One such example is imbalanced data classification, where, on the one hand, we want to achieve the best possible classification quality for data from the minority class without degrading the classification quality of the majority class. One solution is to propose an aggregate learning criterion and reduce the multi-objective learning task to a single-criteria optimization problem. Unfortunately, such an approach is characterized by ambiguity of interpretation since the value of the aggregated criterion does not indicate the value of the component criteria. Hence, there are more and more proposals for algorithms based on multi-objective optimization (MOO), which can simultaneously optimize multiple criteria. However, such an approach results in a set of multiple non-dominated solutions (Pareto front). The selection of a single solution from the Pareto front is a challenge itself, and much attention is paid to the issue of how to select it considering user preferences, as well as how to compare solutions returned by different MOO algorithms among themselves. Thus, a significant gap has been identified in the classifier evaluation methodology, i.e., how to reliably compare methods returning single solutions with algorithms returning solutions in the form of Pareto fronts. To fill the aforementioned gap, this article proposes a new, reliable way of evaluating algorithms based on multi-objective algorithms with methods that return single solutions while pointing out solutions from a Pareto front tailored to the user's preferences. This work focuses only on algorithm comparison, not their learning. The algorithms selected for this study are illustrative to help understand the proposed approach. --- ### Scaling Law Analysis in Federated Learning: How to Select the Optimal Model Size? Authors: Xuanyu Chen, Nan Yang, Shuai Wang, Dong Yuan Published: 2025-11-15 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.12188v1 The recent success of large language models (LLMs) has sparked a growing interest in training large-scale models. As the model size continues to scale, concerns are growing about the depletion of high-quality, well-curated training data. This has led practitioners to explore training approaches like Federated Learning (FL), which can leverage the abundant data on edge devices while maintaining privacy. However, the decentralization of training datasets in FL introduces challenges to scaling large models, a topic that remains under-explored. This paper fills this gap and provides qualitative insights on generalizing the previous model scaling experience to federated learning scenarios. Specifically, we derive a PAC-Bayes (Probably Approximately Correct Bayesian) upper bound for the generalization error of models trained with stochastic algorithms in federated settings and quantify the impact of distributed training data on the optimal model size by finding the analytic solution of model size that minimizes this bound. Our theoretical results demonstrate that the optimal model size has a negative power law relationship with the number of clients if the total training compute is unchanged. Besides, we also find that switching to FL with the same training compute will inevitably reduce the upper bound of generalization performance that the model can achieve through training, and that estimating the optimal model size in federated scenarios should depend on the average training compute across clients. Furthermore, we also empirically validate the correctness of our results with extensive training runs on different models, network settings, and datasets. --- ### Chemistry-Enhanced Diffusion-Based Framework for Small-to-Large Molecular Conformation Generation Authors: Yifei Zhu, Jiahui Zhang, Jiawei Peng, Mengge Li, Chao Xu, Zhenggang Lan Published: 2025-11-15 Categories: physics.chem-ph, cs.LG arXiv: https://arxiv.org/abs/2511.12182v1 Obtaining 3D conformations of realistic polyatomic molecules at the quantum chemistry level remains challenging, and although recent machine learning advances offer promise, predicting large-molecule structures still requires substantial computational effort. Here, we introduce StoL, a diffusion model-based framework that enables rapid and knowledge-free generation of large molecular structures from small-molecule data. Remarkably, StoL assembles molecules in a LEGO-style fashion from scratch, without seeing the target molecules or any structures of comparable size during training. Given a SMILES input, it decomposes the molecule into chemically valid fragments, generates their 3D structures with a diffusion model trained on small molecules, and assembles them into diverse conformations. This fragment-based strategy eliminates the need for large-molecule training data while maintaining high scalability and transferability. By embedding chemical principles into key steps, StoL ensures faster convergence, chemically rational structures, and broad configurational coverage, as confirmed against DFT calculations. --- ### MixAR: Mixture Autoregressive Image Generation Authors: Jinyuan Hu, Jiayou Zhang, Shaobo Cui, Kun Zhang, Guangyi Chen Published: 2025-11-15 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2511.12181v1 Autoregressive (AR) approaches, which represent images as sequences of discrete tokens from a finite codebook, have achieved remarkable success in image generation. However, the quantization process and the limited codebook size inevitably discard fine-grained information, placing bottlenecks on fidelity. Motivated by this limitation, recent studies have explored autoregressive modeling in continuous latent spaces, which offers higher generation quality. Yet, unlike discrete tokens constrained by a fixed codebook, continuous representations lie in a vast and unstructured space, posing significant challenges for efficient autoregressive modeling. To address these challenges, we introduce MixAR, a novel framework that leverages mixture training paradigms to inject discrete tokens as prior guidance for continuous AR modeling. MixAR is a factorized formulation that leverages discrete tokens as prior guidance for continuous autoregressive prediction. We investigate several discrete-continuous mixture strategies, including self-attention (DC-SA), cross-attention (DC-CA), and a simple approach (DC-Mix) that replaces homogeneous mask tokens with informative discrete counterparts. Moreover, to bridge the gap between ground-truth training tokens and inference tokens produced by the pre-trained AR model, we propose Training-Inference Mixture (TI-Mix) to achieve consistent training and generation distributions. In our experiments, we demonstrate a favorable balance of the DC-Mix strategy between computational efficiency and generation fidelity, and consistent improvement of TI-Mix. --- ### Understanding InfoNCE: Transition Probability Matrix Induced Feature Clustering Authors: Ge Cheng, Shuo Wang, Yun Zhang Published: 2025-11-15 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2511.12180v1 Contrastive learning has emerged as a cornerstone of unsupervised representation learning across vision, language, and graph domains, with InfoNCE as its dominant objective. Despite its empirical success, the theoretical underpinnings of InfoNCE remain limited. In this work, we introduce an explicit feature space to model augmented views of samples and a transition probability matrix to capture data augmentation dynamics. We demonstrate that InfoNCE optimizes the probability of two views sharing the same source toward a constant target defined by this matrix, naturally inducing feature clustering in the representation space. Leveraging this insight, we propose Scaled Convergence InfoNCE (SC-InfoNCE), a novel loss function that introduces a tunable convergence target to flexibly control feature similarity alignment. By scaling the target matrix, SC-InfoNCE enables flexible control over feature similarity alignment, allowing the training objective to better match the statistical properties of downstream data. Experiments on benchmark datasets, including image, graph, and text tasks, show that SC-InfoNCE consistently achieves strong and reliable performance across diverse domains. --- ### Reinforcement Learning for Charging Optimization of Inhomogeneous Dicke Quantum Batteries Authors: Xiaobin Song, Siyuan Bai, Da-Wei Wang, Hanxiao Tao, Xizhe Wang, Rebing Wu, Benben Jiang Published: 2025-11-15 Categories: quant-ph, cs.AI arXiv: https://arxiv.org/abs/2511.12176v2 Charging optimization is a key challenge to the implementation of quantum batteries, particularly under inhomogeneity and partial observability. This paper employs reinforcement learning to optimize piecewise-constant charging policies for an inhomogeneous Dicke battery. We systematically compare policies across four observability regimes, from full-state access to experimentally accessible observables (energies of individual two-level systems (TLSs), first-order averages, and second-order correlations). Simulation results demonstrate that full observability yields near-optimal ergotropy with low variability, while under partial observability, access to only single-TLS energies or energies plus first-order averages lags behind the fully observed baseline. However, augmenting partial observations with second-order correlations recovers most of the gap, reaching 94%-98% of the full-state baseline. The learned schedules are nonmyopic, trading temporary plateaus or declines for superior terminal outcomes. These findings highlight a practical route to effective fast-charging protocols under realistic information constraints. --- ### AI-Enhanced IoT Systems for Predictive Maintenance and Affordability Optimization in Smart Microgrids: A Digital Twin Approach Authors: Koushik Ahmed Kushal, Florimond Gueniat Published: 2025-11-15 Categories: eess.SY, cs.AI arXiv: https://arxiv.org/abs/2511.12175v1 This study presents an AI enhanced IoT framework for predictive maintenance and affordability optimization in smart microgrids using a Digital Twin modeling approach. The proposed system integrates real time sensor data, machine learning based fault prediction, and cost aware operational analytics to improve reliability and energy efficiency in distributed microgrid environments. By synchronizing physical microgrid components with a virtual Digital Twin, the framework enables early detection of component degradation, dynamic load management, and optimized maintenance scheduling. Experimental evaluations demonstrate improved predictive accuracy, reduced operational downtime, and measurable cost savings compared to baseline microgrid management methods. The findings highlight the potential of Digital Twin driven IoT architectures as a scalable solution for next generation intelligent and affordable energy systems. --- ### TSGDiff: Rethinking Synthetic Time Series Generation from a Pure Graph Perspective Authors: Lifeng Shen, Xuyang Li, Lele Long Published: 2025-11-15 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.12174v1 Diffusion models have shown great promise in data generation, yet generating time series data remains challenging due to the need to capture complex temporal dependencies and structural patterns. In this paper, we present \textit{TSGDiff}, a novel framework that rethinks time series generation from a graph-based perspective. Specifically, we represent time series as dynamic graphs, where edges are constructed based on Fourier spectrum characteristics and temporal dependencies. A graph neural network-based encoder-decoder architecture is employed to construct a latent space, enabling the diffusion process to model the structural representation distribution of time series effectively. Furthermore, we propose the Topological Structure Fidelity (Topo-FID) score, a graph-aware metric for assessing the structural similarity of time series graph representations. Topo-FID integrates two sub-metrics: Graph Edit Similarity, which quantifies differences in adjacency matrices, and Structural Entropy Similarity, which evaluates the entropy of node degree distributions. This comprehensive metric provides a more accurate assessment of structural fidelity in generated time series. Experiments on real-world datasets demonstrate that \textit{TSGDiff} generates high-quality synthetic time series data generation, faithfully preserving temporal dependencies and structural integrity, thereby advancing the field of synthetic time series generation. --- ### FGM optimization in complex domains using Gaussian process regression based profile generation algorithm Authors: Chaitanya Kumar Konda, Piyush Agrawal, Shivansh Srivastava, Manish Agrawal Published: 2025-11-15 Categories: cs.LG, physics.comp-ph arXiv: https://arxiv.org/abs/2511.12171v1 This manuscript addresses the challenge of designing functionally graded materials (FGMs) for arbitrary-shaped domains. Towards this goal, the present work proposes a generic volume fraction profile generation algorithm based on Gaussian Process Regression (GPR). The proposed algorithm can handle complex-shaped domains and generate smooth FGM profiles while adhering to the specified volume fraction values at boundaries/part of boundaries. The resulting design space from GPR comprises diverse profiles, enhancing the potential for discovering optimal configurations. Further, the algorithm allows the user to control the smoothness of the underlying profiles and the size of the design space through a length scale parameter. Further, the proposed profile generation scheme is coupled with the genetic algorithm to find the optimum FGM profiles for a given application. To make the genetic algorithm consistent with the GPR profile generation scheme, the standard simulated binary crossover operator in the genetic algorithm has been modified with a projection operator. We present numerous thermoelastic optimization examples to demonstrate the efficacy of the proposed profile generation algorithm and optimization framework. --- ### Rethinking Multimodal Point Cloud Completion: A Completion-by-Correction Perspective Authors: Wang Luo, Di Wu, Hengyuan Na, Yinlin Zhu, Miao Hu, Guocong Quan Published: 2025-11-15 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2511.12170v2 Point cloud completion aims to reconstruct complete 3D shapes from partial observations, which is a challenging problem due to severe occlusions and missing geometry. Despite recent advances in multimodal techniques that leverage complementary RGB images to compensate for missing geometry, most methods still follow a Completion-by-Inpainting paradigm, synthesizing missing structures from fused latent features. We empirically show that this paradigm often results in structural inconsistencies and topological artifacts due to limited geometric and semantic constraints. To address this, we rethink the task and propose a more robust paradigm, termed Completion-by-Correction, which begins with a topologically complete shape prior generated by a pretrained image-to-3D model and performs feature-space correction to align it with the partial observation. This paradigm shifts completion from unconstrained synthesis to guided refinement, enabling structurally consistent and observation-aligned reconstruction. Building upon this paradigm, we introduce PGNet, a multi-stage framework that conducts dual-feature encoding to ground the generative prior, synthesizes a coarse yet structurally aligned scaffold, and progressively refines geometric details via hierarchical correction. Experiments on the ShapeNetViPC dataset demonstrate the superiority of PGNet over state-of-the-art baselines in terms of average Chamfer Distance (-23.5%) and F-score (+7.1%). --- ### Incremental Maintenance of DatalogMTL Materialisations Authors: Kaiyue Zhao, Dingqi Chen, Shaoyu Wang, Pan Hu Published: 2025-11-15 Categories: cs.AI arXiv: https://arxiv.org/abs/2511.12169v3 DatalogMTL extends the classical Datalog language with metric temporal logic (MTL), enabling expressive reasoning over temporal data. While existing reasoning approaches, such as materialisation based and automata based methods, offer soundness and completeness, they lack support for handling efficient dynamic updates, a crucial requirement for real-world applications that involve frequent data updates. In this work, we propose DRedMTL, an incremental reasoning algorithm for DatalogMTL with bounded intervals. Our algorithm builds upon the classical DRed algorithm, which incrementally updates the materialisation of a Datalog program. Unlike a Datalog materialisation which is in essence a finite set of facts, a DatalogMTL materialisation has to be represented as a finite set of facts plus periodic intervals indicating how the full materialisation can be constructed through unfolding. To cope with this, our algorithm is equipped with specifically designed operators to efficiently handle such periodic representations of DatalogMTL materialisations. We have implemented this approach and tested it on several publicly available datasets. Experimental results show that DRedMTL often significantly outperforms rematerialisation, sometimes by orders of magnitude. --- ### Rapid Machine Learning-Driven Detection of Pesticides and Dyes Using Raman Spectroscopy Authors: Quach Thi Thai Binh, Thuan Phuoc, Xuan Hai, Thang Bach Phan, Vu Thi Hanh Thu, Nguyen Tuan Hung Published: 2025-11-15 Categories: cond-mat.mtrl-sci, cs.LG arXiv: https://arxiv.org/abs/2511.12167v1 The extensive use of pesticides and synthetic dyes poses critical threats to food safety, human health, and environmental sustainability, necessitating rapid and reliable detection methods. Raman spectroscopy offers molecularly specific fingerprints but suffers from spectral noise, fluorescence background, and band overlap, limiting its real-world applicability. Here, we propose a deep learning framework based on ResNet-18 feature extraction, combined with advanced classifiers, including XGBoost, SVM, and their hybrid integration, to detect pesticides and dyes from Raman spectroscopy, called MLRaman. The MLRaman with the CNN-XGBoost model achieved a predictive accuracy of 97.4% and a perfect AUC of 1.0, while it with the CNN-SVM model provided competitive results with robust class-wise discrimination. Dimensionality reduction analyses (PCA, t-SNE, UMAP) confirmed the separability of Raman embeddings across 10 analytes, including 7 pesticides and 3 dyes. Finally, we developed a user-friendly Streamlit application for real-time prediction, which successfully identified unseen Raman spectra from our independent experiments and also literature sources, underscoring strong generalization capacity. This study establishes a scalable, practical MLRaman model for multi-residue contaminant monitoring, with significant potential for deployment in food safety and environmental surveillance. --- ### Codebook-Centric Deep Hashing: End-to-End Joint Learning of Semantic Hash Centers and Neural Hash Function Authors: Shuo Yin, Zhiyuan Yin, Yuqing Hou, Rui Liu, Yong Chen, Dell Zhang Published: 2025-11-15 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2511.12162v1 Hash center-based deep hashing methods improve upon pairwise or triplet-based approaches by assigning fixed hash centers to each class as learning targets, thereby avoiding the inefficiency of local similarity optimization. However, random center initialization often disregards inter-class semantic relationships. While existing two-stage methods mitigate this by first refining hash centers with semantics and then training the hash function, they introduce additional complexity, computational overhead, and suboptimal performance due to stage-wise discrepancies. To address these limitations, we propose $\textbf{Center-Reassigned Hashing (CRH)}$, an end-to-end framework that $\textbf{dynamically reassigns hash centers}$ from a preset codebook while jointly optimizing the hash function. Unlike previous methods, CRH adapts hash centers to the data distribution $\textbf{without explicit center optimization phases}$, enabling seamless integration of semantic relationships into the learning process. Furthermore, $\textbf{a multi-head mechanism}$ enhances the representational capacity of hash centers, capturing richer semantic structures. Extensive experiments on three benchmarks demonstrate that CRH learns semantically meaningful hash centers and outperforms state-of-the-art deep hashing methods in retrieval tasks. --- ### CriticSearch: Fine-Grained Credit Assignment for Search Agents via a Retrospective Critic Authors: Yaocheng Zhang, Haohuan Huang, Zijun Song, Yuanheng Zhu, Qichao Zhang, Zijie Zhao, Dongbin Zhao Published: 2025-11-15 Categories: cs.CL arXiv: https://arxiv.org/abs/2511.12159v1 Tool-Integrated Reasoning (TIR) with search engines enables large language models to iteratively retrieve up-to-date external knowledge, enhancing adaptability and generalization in complex question-answering tasks. However, existing search agent pipelines typically depend on reinforcement learning based optimization, which often suffers from sparse outcome rewards, leading to inefficient exploration and unstable training. We introduce CriticSearch, a fine-grained credit-assignment framework that supplies dense, turn-level feedback via a retrospective critic mechanism. During training, a frozen, asymmetric critique LLM retrospectively evaluates each turn using privileged information from the full trajectory and gold answers, converting these assessments into stable, dense rewards that guide policy improvement. Experimental results across diverse multi-hop reasoning benchmarks demonstrate that CriticSearch consistently outperforms existing baselines, achieving faster convergence, improved training stability, and higher performance. --- ### Data-Efficient Self-Supervised Algorithms for Fine-Grained Birdsong Analysis Authors: Houtan Ghaffari, Lukas Rauch, Paul Devos Published: 2025-11-15 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.12158v3 Research in bioacoustics, neuroscience, and linguistics often uses birdsong as a proxy to acquire knowledge across diverse areas. This requires audio models to annotate and parse the birdsong. Developing such models requires precise, syllable-level annotated training data. Therefore, automated methods that reduce annotation costs are in demand. This work presents a data-efficient birdsong annotator called Residual Multi-Layer Perceptron Recurrent Neural Network. It then presents a three-stage training pipeline for developing reliable birdsong syllable detectors with minimal annotation. The first stage is self-supervised learning from unlabeled data. Two of the most successful pretraining paradigms are explored, namely, masked prediction and online clustering. The second stage is supervised training with effective data augmentation to produce a robust frame-level syllable detector for each individual. The third stage is a semi-supervised post-training step that refines each individual's model using unlabeled data. The effectiveness of this approach is demonstrated for the Canary song in extreme label-scarcity scenarios. From a signal-processing perspective, the Canary song exhibits one of the most challenging spectro-temporal patterns for algorithmic time-series annotation: rapid vocalizations, brief inter-syllabic intervals, fast and broadband frequency sweeps, and spectrally similar syllables that require fine-grained features to distinguish. Hence, a successful syllable detection algorithm for Canary also establishes a robust baseline for other birds. This methodological generalization is validated in a case study of Bengalese Finch song annotation. Finally, the potential of self-supervised embeddings is assessed for linear probing and unsupervised birdsong analysis. --- ### Rethinking Deep Alignment Through The Lens Of Incomplete Learning Authors: Thong Bach, Dung Nguyen, Thao Minh Le, Truyen Tran Published: 2025-11-15 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.12155v1 Large language models exhibit systematic vulnerabilities to adversarial attacks despite extensive safety alignment. We provide a mechanistic analysis revealing that position-dependent gradient weakening during autoregressive training creates signal decay, leading to incomplete safety learning where safety training fails to transform model preferences in later response regions fully. We introduce base-favored tokens -- vocabulary elements where base models assign higher probability than aligned models -- as computational indicators of incomplete safety learning and develop a targeted completion method that addresses undertrained regions through adaptive penalties and hybrid teacher distillation. Experimental evaluation across Llama and Qwen model families demonstrates dramatic improvements in adversarial robustness, with 48--98% reductions in attack success rates while preserving general capabilities. These results establish both a mechanistic understanding and practical solutions for fundamental limitations in safety alignment methodologies. --- ### Open Banking Foundational Model: Learning Language Representations from Few Financial Transactions Authors: Gustavo Polleti, Marlesson Santana, Eduardo Fontes Published: 2025-11-15 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2511.12154v1 We introduced a multimodal foundational model for financial transactions that integrates both structured attributes and unstructured textual descriptions into a unified representation. By adapting masked language modeling to transaction sequences, we demonstrated that our approach not only outperforms classical feature engineering and discrete event sequence methods but is also particularly effective in data-scarce Open Banking scenarios. To our knowledge, this is the first large-scale study across thousands of financial institutions in North America, providing evidence that multimodal representations can generalize across geographies and institutions. These results highlight the potential of self-supervised models to advance financial applications ranging from fraud prevention and credit risk to customer insights --- ### FIA-Edit: Frequency-Interactive Attention for Efficient and High-Fidelity Inversion-Free Text-Guided Image Editing Authors: Kaixiang Yang, Boyang Shen, Xin Li, Yuchen Dai, Yuxuan Luo, Yueran Ma, Wei Fang, Qiang Li, Zhiwei Wang Published: 2025-11-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.12151v1 Text-guided image editing has advanced rapidly with the rise of diffusion models. While flow-based inversion-free methods offer high efficiency by avoiding latent inversion, they often fail to effectively integrate source information, leading to poor background preservation, spatial inconsistencies, and over-editing due to the lack of effective integration of source information. In this paper, we present FIA-Edit, a novel inversion-free framework that achieves high-fidelity and semantically precise edits through a Frequency-Interactive Attention. Specifically, we design two key components: (1) a Frequency Representation Interaction (FRI) module that enhances cross-domain alignment by exchanging frequency components between source and target features within self-attention, and (2) a Feature Injection (FIJ) module that explicitly incorporates source-side queries, keys, values, and text embeddings into the target branch's cross-attention to preserve structure and semantics. Comprehensive and extensive experiments demonstrate that FIA-Edit supports high-fidelity editing at low computational cost (~6s per 512 * 512 image on an RTX 4090) and consistently outperforms existing methods across diverse tasks in visual quality, background fidelity, and controllability. Furthermore, we are the first to extend text-guided image editing to clinical applications. By synthesizing anatomically coherent hemorrhage variations in surgical images, FIA-Edit opens new opportunities for medical data augmentation and delivers significant gains in downstream bleeding classification. Our project is available at: https://github.com/kk42yy/FIA-Edit. --- ### Breaking the Modality Wall: Time-step Mixup for Efficient Spiking Knowledge Transfer from Static to Event Domain Authors: Yuqi Xie, Shuhan Ye, Yi Yu, Chong Wang, Qixin Zhang, Jiazhen Xu, Le Shen, Yuanbin Qian, Jiangbo Qian, Guoqi Li Published: 2025-11-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.12150v1 The integration of event cameras and spiking neural networks (SNNs) promises energy-efficient visual intelligence, yet scarce event data and the sparsity of DVS outputs hinder effective training. Prior knowledge transfers from RGB to DVS often underperform because the distribution gap between modalities is substantial. In this work, we present Time-step Mixup Knowledge Transfer (TMKT), a cross-modal training framework with a probabilistic Time-step Mixup (TSM) strategy. TSM exploits the asynchronous nature of SNNs by interpolating RGB and DVS inputs at various time steps to produce a smooth curriculum within each sequence, which reduces gradient variance and stabilizes optimization with theoretical analysis. To employ auxiliary supervision from TSM, TMKT introduces two lightweight modality-aware objectives, Modality Aware Guidance (MAG) for per-frame source supervision and Mixup Ratio Perception (MRP) for sequence-level mix ratio estimation, which explicitly align temporal features with the mixing schedule. TMKT enables smoother knowledge transfer, helps mitigate modality mismatch during training, and achieves superior performance in spiking image classification tasks. Extensive experiments across diverse benchmarks and multiple SNN backbones, together with ablations, demonstrate the effectiveness of our method. --- ### AttackVLA: Benchmarking Adversarial and Backdoor Attacks on Vision-Language-Action Models Authors: Jiayu Li, Yunhan Zhao, Xiang Zheng, Zonghuan Xu, Yige Li, Xingjun Ma, Yu-Gang Jiang Published: 2025-11-15 Categories: cs.CR, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2511.12149v1 Vision-Language-Action (VLA) models enable robots to interpret natural-language instructions and perform diverse tasks, yet their integration of perception, language, and control introduces new safety vulnerabilities. Despite growing interest in attacking such models, the effectiveness of existing techniques remains unclear due to the absence of a unified evaluation framework. One major issue is that differences in action tokenizers across VLA architectures hinder reproducibility and fair comparison. More importantly, most existing attacks have not been validated in real-world scenarios. To address these challenges, we propose AttackVLA, a unified framework that aligns with the VLA development lifecycle, covering data construction, model training, and inference. Within this framework, we implement a broad suite of attacks, including all existing attacks targeting VLAs and multiple adapted attacks originally developed for vision-language models, and evaluate them in both simulation and real-world settings. Our analysis of existing attacks reveals a critical gap: current methods tend to induce untargeted failures or static action states, leaving targeted attacks that drive VLAs to perform precise long-horizon action sequences largely unexplored. To fill this gap, we introduce BackdoorVLA, a targeted backdoor attack that compels a VLA to execute an attacker-specified long-horizon action sequence whenever a trigger is present. We evaluate BackdoorVLA in both simulated benchmarks and real-world robotic settings, achieving an average targeted success rate of 58.4% and reaching 100% on selected tasks. Our work provides a standardized framework for evaluating VLA vulnerabilities and demonstrates the potential for precise adversarial manipulation, motivating further research on securing VLA-based embodied systems. --- ### Finding Time Series Anomalies using Granular-ball Vector Data Description Authors: Lifeng Shen, Liang Peng, Ruiwen Liu, Shuyin Xia, Yi Liu Published: 2025-11-15 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2511.12147v1 Modeling normal behavior in dynamic, nonlinear time series data is challenging for effective anomaly detection. Traditional methods, such as nearest neighbor and clustering approaches, often depend on rigid assumptions, such as a predefined number of reliable neighbors or clusters, which frequently break down in complex temporal scenarios. To address these limitations, we introduce the Granular-ball One-Class Network (GBOC), a novel approach based on a data-adaptive representation called Granular-ball Vector Data Description (GVDD). GVDD partitions the latent space into compact, high-density regions represented by granular-balls, which are generated through a density-guided hierarchical splitting process and refined by removing noisy structures. Each granular-ball serves as a prototype for local normal behavior, naturally positioning itself between individual instances and clusters while preserving the local topological structure of the sample set. During training, GBOC improves the compactness of representations by aligning samples with their nearest granular-ball centers. During inference, anomaly scores are computed based on the distance to the nearest granular-ball. By focusing on dense, high-quality regions and significantly reducing the number of prototypes, GBOC delivers both robustness and efficiency in anomaly detection. Extensive experiments validate the effectiveness and superiority of the proposed method, highlighting its ability to handle the challenges of time series anomaly detection. --- ### Variation-Bounded Loss for Noise-Tolerant Learning Authors: Jialiang Wang, Xiong Zhou, Xianming Liu, Gangfeng Hu, Deming Zhai, Junjun Jiang, Haoliang Li Published: 2025-11-15 Categories: cs.LG, cs.CV arXiv: https://arxiv.org/abs/2511.12143v1 Mitigating the negative impact of noisy labels has been aperennial issue in supervised learning. Robust loss functions have emerged as a prevalent solution to this problem. In this work, we introduce the Variation Ratio as a novel property related to the robustness of loss functions, and propose a new family of robust loss functions, termed Variation-Bounded Loss (VBL), which is characterized by a bounded variation ratio. We provide theoretical analyses of the variation ratio, proving that a smaller variation ratio would lead to better robustness. Furthermore, we reveal that the variation ratio provides a feasible method to relax the symmetric condition and offers a more concise path to achieve the asymmetric condition. Based on the variation ratio, we reformulate several commonly used loss functions into a variation-bounded form for practical applications. Positive experiments on various datasets exhibit the effectiveness and flexibility of our approach. --- ### MAVIS: A Benchmark for Multimodal Source Attribution in Long-form Visual Question Answering Authors: Seokwon Song, Minsu Park, Gunhee Kim Published: 2025-11-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.12142v2 Source attribution aims to enhance the reliability of AI-generated answers by including references for each statement, helping users validate the provided answers. However, existing work has primarily focused on text-only scenario and largely overlooked the role of multimodality. We introduce MAVIS, the first benchmark designed to evaluate multimodal source attribution systems that understand user intent behind visual questions, retrieve multimodal evidence, and generate long-form answers with citations. Our dataset comprises 157K visual QA instances, where each answer is annotated with fact-level citations referring to multimodal documents. We develop fine-grained automatic metrics along three dimensions of informativeness, groundedness, and fluency, and demonstrate their strong correlation with human judgments. Our key findings are threefold: (1) LVLMs with multimodal RAG generate more informative and fluent answers than unimodal RAG, but they exhibit weaker groundedness for image documents than for text documents, a gap amplified in multimodal settings. (2) Given the same multimodal documents, there is a trade-off between informativeness and groundedness across different prompting methods. (3) Our proposed method highlights mitigating contextual bias in interpreting image documents as a crucial direction for future research. --- ### Seeing is Believing: Rich-Context Hallucination Detection for MLLMs via Backward Visual Grounding Authors: Pinxue Guo, Chongruo Wu, Xinyu Zhou, Lingyi Hong, Zhaoyu Chen, Jinglun Li, Kaixun Jiang, Sen-ching Samson Cheung, Wei Zhang, Wenqiang Zhang Published: 2025-11-15 Categories: cs.CL, cs.CV arXiv: https://arxiv.org/abs/2511.12140v1 Multimodal Large Language Models (MLLMs) have unlocked powerful cross-modal capabilities, but still significantly suffer from hallucinations. As such, accurate detection of hallucinations in MLLMs is imperative for ensuring their reliability in practical applications. To this end, guided by the principle of "Seeing is Believing", we introduce VBackChecker, a novel reference-free hallucination detection framework that verifies the consistency of MLLMgenerated responses with visual inputs, by leveraging a pixellevel Grounding LLM equipped with reasoning and referring segmentation capabilities. This reference-free framework not only effectively handles rich-context scenarios, but also offers interpretability. To facilitate this, an innovative pipeline is accordingly designed for generating instruction-tuning data (R-Instruct), featuring rich-context descriptions, grounding masks, and hard negative samples. We further establish R^2 -HalBench, a new hallucination benchmark for MLLMs, which, unlike previous benchmarks, encompasses real-world, rich-context descriptions from 18 MLLMs with high-quality annotations, spanning diverse object-, attribute, and relationship-level details. VBackChecker outperforms prior complex frameworks and achieves state-of-the-art performance on R^2 -HalBench, even rivaling GPT-4o's capabilities in hallucination detection. It also surpasses prior methods in the pixel-level grounding task, achieving over a 10% improvement. All codes, data, and models are available at https://github.com/PinxueGuo/VBackChecker. --- ### Fusion-ResNet: A Lightweight multi-label NILM Model Using PCA-ICA Feature Fusion Authors: Sahar Moghimian Hoosh, Ilia Kamyshev, Henni Ouerdane Published: 2025-11-15 Categories: cs.LG, eess.SY arXiv: https://arxiv.org/abs/2511.12139v1 Non-intrusive load monitoring (NILM) is an advanced load monitoring technique that uses data-driven algorithms to disaggregate the total power consumption of a household into the consumption of individual appliances. However, real-world NILM deployment still faces major challenges, including overfitting, low model generalization, and disaggregating a large number of appliances operating at the same time. To address these challenges, this work proposes an end-to-end framework for the NILM classification task, which consists of high-frequency labeled data, a feature extraction method, and a lightweight neural network. Within this framework, we introduce a novel feature extraction method that fuses Independent Component Analysis (ICA) and Principal Component Analysis (PCA) features. Moreover, we propose a lightweight architecture for multi-label NILM classification (Fusion-ResNet). The proposed feature-based model achieves a higher $F1$ score on average and across different appliances compared to state-of-the-art NILM classifiers while minimizing the training and inference time. Finally, we assessed the performance of our model against baselines with a varying number of simultaneously active devices. Results demonstrate that Fusion-ResNet is relatively robust to stress conditions with up to 15 concurrently active appliances. --- ### Compression and Inference of Spiking Neural Networks on Resource-Constrained Hardware Authors: Karol C. Jurzec, Tomasz Szydlo, Maciej Wielgosz Published: 2025-11-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.12136v1 Spiking neural networks (SNNs) communicate via discrete spikes in time rather than continuous activations. Their event-driven nature offers advantages for temporal processing and energy efficiency on resource-constrained hardware, but training and deployment remain challenging. We present a lightweight C-based runtime for SNN inference on edge devices and optimizations that reduce latency and memory without sacrificing accuracy. Trained models exported from SNNTorch are translated to a compact C representation; static, cache-friendly data layouts and preallocation avoid interpreter and allocation overheads. We further exploit sparse spiking activity to prune inactive neurons and synapses, shrinking computation in upstream convolutional layers. Experiments on N-MNIST and ST-MNIST show functional parity with the Python baseline while achieving ~10 speedups on desktop CPU and additional gains with pruning, together with large memory reductions that enable microcontroller deployment (Arduino Portenta H7). Results indicate that SNNs can be executed efficiently on conventional embedded platforms when paired with an optimized runtime and spike-driven model compression. Code: https://github.com/karol-jurzec/snn-generator/ --- ### RTMol: Rethinking Molecule-text Alignment in a Round-trip View Authors: Letian Chen, Runhan Shi, Gufeng Yu, Yang Yang Published: 2025-11-15 Categories: cs.AI, cs.LG, q-bio.BM arXiv: https://arxiv.org/abs/2511.12135v2 Aligning molecular sequence representations (e.g., SMILES notations) with textual descriptions is critical for applications spanning drug discovery, materials design, and automated chemical literature analysis. Existing methodologies typically treat molecular captioning (molecule-to-text) and text-based molecular design (text-to-molecule) as separate tasks, relying on supervised fine-tuning or contrastive learning pipelines. These approaches face three key limitations: (i) conventional metrics like BLEU prioritize linguistic fluency over chemical accuracy, (ii) training datasets frequently contain chemically ambiguous narratives with incomplete specifications, and (iii) independent optimization of generation directions leads to bidirectional inconsistency. To address these issues, we propose RTMol, a bidirectional alignment framework that unifies molecular captioning and text-to-SMILES generation through self-supervised round-trip learning. The framework introduces novel round-trip evaluation metrics and enables unsupervised training for molecular captioning without requiring paired molecule-text corpora. Experiments demonstrate that RTMol enhances bidirectional alignment performance by up to 47% across various LLMs, establishing an effective paradigm for joint molecule-text understanding and generation. --- ### AI-Salesman: Towards Reliable Large Language Model Driven Telemarketing Authors: Qingyu Zhang, Chunlei Xin, Xuanang Chen, Yaojie Lu, Hongyu Lin, Xianpei Han, Le Sun, Qing Ye, Qianlong Xie, Xingxing Wang Published: 2025-11-15 Categories: cs.CL arXiv: https://arxiv.org/abs/2511.12133v1 Goal-driven persuasive dialogue, exemplified by applications like telemarketing, requires sophisticated multi-turn planning and strict factual faithfulness, which remains a significant challenge for even state-of-the-art Large Language Models (LLMs). A lack of task-specific data often limits previous works, and direct LLM application suffers from strategic brittleness and factual hallucination. In this paper, we first construct and release TeleSalesCorpus, the first real-world-grounded dialogue dataset for this domain. We then propose AI-Salesman, a novel framework featuring a dual-stage architecture. For the training stage, we design a Bayesian-supervised reinforcement learning algorithm that learns robust sales strategies from noisy dialogues. For the inference stage, we introduce the Dynamic Outline-Guided Agent (DOGA), which leverages a pre-built script library to provide dynamic, turn-by-turn strategic guidance. Moreover, we design a comprehensive evaluation framework that combines fine-grained metrics for key sales skills with the LLM-as-a-Judge paradigm. Experimental results demonstrate that our proposed AI-Salesman significantly outperforms baseline models in both automatic metrics and comprehensive human evaluations, showcasing its effectiveness in complex persuasive scenarios. --- ### FairGSE: Fairness-Aware Graph Neural Network without High False Positive Rates Authors: Zhenqiang Ye, Jinjie Lu, Tianlong Gu, Fengrui Hao, Xuemin Wang Published: 2025-11-15 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.12132v1 Graph neural networks (GNNs) have emerged as the mainstream paradigm for graph representation learning due to their effective message aggregation. However, this advantage also amplifies biases inherent in graph topology, raising fairness concerns. Existing fairness-aware GNNs provide satisfactory performance on fairness metrics such as Statistical Parity and Equal Opportunity while maintaining acceptable accuracy trade-offs. Unfortunately, we observe that this pursuit of fairness metrics neglects the GNN's ability to predict negative labels, which renders their predictions with extremely high False Positive Rates (FPR), resulting in negative effects in high-risk scenarios. To this end, we advocate that classification performance should be carefully calibrated while improving fairness, rather than simply constraining accuracy loss. Furthermore, we propose Fair GNN via Structural Entropy (\textbf{FairGSE}), a novel framework that maximizes two-dimensional structural entropy (2D-SE) to improve fairness without neglecting false positives. Experiments on several real-world datasets show FairGSE reduces FPR by 39\% vs. state-of-the-art fairness-aware GNNs, with comparable fairness improvement. --- ### OAD-Promoter: Enhancing Zero-shot VQA using Large Language Models with Object Attribute Description Authors: Quanxing Xu, Ling Zhou, Feifei Zhang, Jinyu Tian, Rubing Huang Published: 2025-11-15 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2511.12131v1 Large Language Models (LLMs) have become a crucial tool in Visual Question Answering (VQA) for handling knowledge-intensive questions in few-shot or zero-shot scenarios. However, their reliance on massive training datasets often causes them to inherit language biases during the acquisition of knowledge. This limitation imposes two key constraints on existing methods: (1) LLM predictions become less reliable due to bias exploitation, and (2) despite strong knowledge reasoning capabilities, LLMs still struggle with out-of-distribution (OOD) generalization. To address these issues, we propose Object Attribute Description Promoter (OAD-Promoter), a novel approach for enhancing LLM-based VQA by mitigating language bias and improving domain-shift robustness. OAD-Promoter comprises three components: the Object-concentrated Example Generation (OEG) module, the Memory Knowledge Assistance (MKA) module, and the OAD Prompt. The OEG module generates global captions and object-concentrated samples, jointly enhancing visual information input to the LLM and mitigating bias through complementary global and regional visual cues. The MKA module assists the LLM in handling OOD samples by retrieving relevant knowledge from stored examples to support questions from unseen domains. Finally, the OAD Prompt integrates the outputs of the preceding modules to optimize LLM inference. Experiments demonstrate that OAD-Promoter significantly improves the performance of LLM-based VQA methods in few-shot or zero-shot settings, achieving new state-of-the-art results. --- ### PRISM of Opinions: A Persona-Reasoned Multimodal Framework for User-centric Conversational Stance Detection Authors: Bingbing Wang, Zhixin Bai, Zhengda Jin, Zihan Wang, Xintong Song, Jingjie Lin, Sixuan Li, Jing Li, Ruifeng Xu Published: 2025-11-15 Categories: cs.CL arXiv: https://arxiv.org/abs/2511.12130v2 The rapid proliferation of multimodal social media content has driven research in Multimodal Conversational Stance Detection (MCSD), which aims to interpret users' attitudes toward specific targets within complex discussions. However, existing studies remain limited by: **1) pseudo-multimodality**, where visual cues appear only in source posts while comments are treated as text-only, misaligning with real-world multimodal interactions; and **2) user homogeneity**, where diverse users are treated uniformly, neglecting personal traits that shape stance expression. To address these issues, we introduce **U-MStance**, the first user-centric MCSD dataset, containing over 40k annotated comments across six real-world targets. We further propose **PRISM**, a **P**ersona-**R**easoned mult**I**modal **S**tance **M**odel for MCSD. PRISM first derives longitudinal user personas from historical posts and comments to capture individual traits, then aligns textual and visual cues within conversational context via Chain-of-Thought to bridge semantic and pragmatic gaps across modalities. Finally, a mutual task reinforcement mechanism is employed to jointly optimize stance detection and stance-aware response generation for bidirectional knowledge transfer. Experiments on U-MStance demonstrate that PRISM yields significant gains over strong baselines, underscoring the effectiveness of user-centric and context-grounded multimodal reasoning for realistic stance understanding. --- ### HCPO: Hierarchical Conductor-Based Policy Optimization in Multi-Agent Reinforcement Learning Authors: Zejiao Liu, Junqi Tu, Yitian Hong, Luolin Xiong, Yaochu Jin, Yang Tang, Fangfei Li Published: 2025-11-15 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.12123v1 In cooperative Multi-Agent Reinforcement Learning (MARL), efficient exploration is crucial for optimizing the performance of joint policy. However, existing methods often update joint policies via independent agent exploration, without coordination among agents, which inherently constrains the expressive capacity and exploration of joint policies. To address this issue, we propose a conductor-based joint policy framework that directly enhances the expressive capacity of joint policies and coordinates exploration. In addition, we develop a Hierarchical Conductor-based Policy Optimization (HCPO) algorithm that instructs policy updates for the conductor and agents in a direction aligned with performance improvement. A rigorous theoretical guarantee further establishes the monotonicity of the joint policy optimization process. By deploying local conductors, HCPO retains centralized training benefits while eliminating inter-agent communication during execution. Finally, we evaluate HCPO on three challenging benchmarks: StarCraftII Multi-agent Challenge, Multi-agent MuJoCo, and Multi-agent Particle Environment. The results indicate that HCPO outperforms competitive MARL baselines regarding cooperative efficiency and stability. --- ### Dynamic Anomaly Identification in Accounting Transactions via Multi-Head Self-Attention Networks Authors: Yi Wang, Ruoyi Fang, Anzhuo Xie, Hanrui Feng, Jianlin Lai Published: 2025-11-15 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.12122v1 This study addresses the problem of dynamic anomaly detection in accounting transactions and proposes a real-time detection method based on a Transformer to tackle the challenges of hidden abnormal behaviors and high timeliness requirements in complex trading environments. The approach first models accounting transaction data by representing multi-dimensional records as time-series matrices and uses embedding layers and positional encoding to achieve low-dimensional mapping of inputs. A sequence modeling structure with multi-head self-attention is then constructed to capture global dependencies and aggregate features from multiple perspectives, thereby enhancing the ability to detect abnormal patterns. The network further integrates feed-forward layers and regularization strategies to achieve deep feature representation and accurate anomaly probability estimation. To validate the effectiveness of the method, extensive experiments were conducted on a public dataset, including comparative analysis, hyperparameter sensitivity tests, environmental sensitivity tests, and data sensitivity tests. Results show that the proposed method outperforms baseline models in AUC, F1-Score, Precision, and Recall, and maintains stable performance under different environmental conditions and data perturbations. These findings confirm the applicability and advantages of the Transformer-based framework for dynamic anomaly detection in accounting transactions and provide methodological support for intelligent financial risk control and auditing. --- ### To Align or Not to Align: Strategic Multimodal Representation Alignment for Optimal Performance Authors: Wanlong Fang, Tianle Zhang, Alvin Chan Published: 2025-11-15 Categories: cs.LG, cs.MM arXiv: https://arxiv.org/abs/2511.12121v4 Multimodal learning often relies on aligning representations across modalities to enable effective information integration, an approach traditionally assumed to be universally beneficial. However, prior research has primarily taken an observational approach, examining naturally occurring alignment in multimodal data and exploring its correlation with model performance, without systematically studying the direct effects of explicitly enforced alignment between representations of different modalities. In this work, we investigate how explicit alignment influences both model performance and representation alignment under different modality-specific information structures. Specifically, we introduce a controllable contrastive learning module that enables precise manipulation of alignment strength during training, allowing us to explore when explicit alignment improves or hinders performance. Our results on synthetic and real datasets under different data characteristics show that the impact of explicit alignment on the performance of unimodal models is related to the characteristics of the data: the optimal level of alignment depends on the amount of redundancy between the different modalities. We identify an optimal alignment strength that balances modality-specific signals and shared redundancy in the mixed information distributions. This work provides practical guidance on when and how explicit alignment should be applied to achieve optimal unimodal encoder performance. --- ### Deep Reinforcement Learning for Automated Stock Trading: An Ensemble Strategy Authors: Hongyang Yang, Xiao-Yang Liu, Shan Zhong, Anwar Walid Published: 2025-11-15 Categories: q-fin.TR, q-fin.CP, q-fin.PM, stat.ML arXiv: https://arxiv.org/abs/2511.12120v1 Stock trading strategies play a critical role in investment. However, it is challenging to design a profitable strategy in a complex and dynamic stock market. In this paper, we propose an ensemble strategy that employs deep reinforcement schemes to learn a stock trading strategy by maximizing investment return. We train a deep reinforcement learning agent and obtain an ensemble trading strategy using three actor-critic based algorithms: Proximal Policy Optimization (PPO), Advantage Actor Critic (A2C), and Deep Deterministic Policy Gradient (DDPG). The ensemble strategy inherits and integrates the best features of the three algorithms, thereby robustly adjusting to different market situations. In order to avoid the large memory consumption in training networks with continuous action space, we employ a load-on-demand technique for processing very large data. We test our algorithms on the 30 Dow Jones stocks that have adequate liquidity. The performance of the trading agent with different reinforcement learning algorithms is evaluated and compared with both the Dow Jones Industrial Average index and the traditional min-variance portfolio allocation strategy. The proposed deep ensemble strategy is shown to outperform the three individual algorithms and two baselines in terms of the risk-adjusted return measured by the Sharpe ratio. This work is fully open-sourced at \href{https://github.com/AI4Finance-Foundation/Deep-Reinforcement-Learning-for-Automated-Stock-Trading-Ensemble-Strategy-ICAIF-2020}{GitHub}. --- ### RadarMP: Motion Perception for 4D mmWave Radar in Autonomous Driving Authors: Ruiqi Cheng, Huijun Di, Jian Li, Feng Liu, Wei Liang Published: 2025-11-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.12117v1 Accurate 3D scene motion perception significantly enhances the safety and reliability of an autonomous driving system. Benefiting from its all-weather operational capability and unique perceptual properties, 4D mmWave radar has emerged as an essential component in advanced autonomous driving. However, sparse and noisy radar points often lead to imprecise motion perception, leaving autonomous vehicles with limited sensing capabilities when optical sensors degrade under adverse weather conditions. In this paper, we propose RadarMP, a novel method for precise 3D scene motion perception using low-level radar echo signals from two consecutive frames. Unlike existing methods that separate radar target detection and motion estimation, RadarMP jointly models both tasks in a unified architecture, enabling consistent radar point cloud generation and pointwise 3D scene flow prediction. Tailored to radar characteristics, we design specialized self-supervised loss functions guided by Doppler shifts and echo intensity, effectively supervising spatial and motion consistency without explicit annotations. Extensive experiments on the public dataset demonstrate that RadarMP achieves reliable motion perception across diverse weather and illumination conditions, outperforming radar-based decoupled motion perception pipelines and enhancing perception capabilities for full-scenario autonomous driving systems. --- ### LLMLagBench: Identifying Temporal Training Boundaries in Large Language Models Authors: Piotr Pęzik, Konrad Kaczyński, Maria Szymańska, Filip Żarnecki, Zuzanna Deckert, Jakub Kwiatkowski, Wojciech Janowski Published: 2025-11-15 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2511.12116v1 Large Language Models (LLMs) are pretrained on textual data up to a specific temporal cutoff. This creates a strict knowledge boundary beyond which models cannot provide accurate information without querying external sources. More subtly, when this limitation is unknown or ignored, LLMs may inadvertently blend outdated time-sensitive information with general knowledge during reasoning tasks, potentially compromising response accuracy. We introduce LLMLagBench, an LLM freshness benchmark, as a systematic approach for identifying the earliest probable temporal boundaries of an LLM's training data by evaluating its knowledge of recent events. We then apply this benchmark to evaluate a large set of LLMs, including models with both explicitly declared and undeclared training cutoffs. The reliability of the benchmark is assessed by manual validation and comparison with publicly released information about LLM pretraining. --- ### MetaGDPO: Alleviating Catastrophic Forgetting with Metacognitive Knowledge through Group Direct Preference Optimization Authors: Lanxue Zhang, Yuqiang Xie, Fang Fang, Fanglong Dong, Rui Liu, Yanan Cao Published: 2025-11-15 Categories: cs.AI arXiv: https://arxiv.org/abs/2511.12113v1 Large Language Models demonstrate strong reasoning capabilities, which can be effectively compressed into smaller models. However, existing datasets and fine-tuning approaches still face challenges that lead to catastrophic forgetting, particularly for models smaller than 8B. First, most datasets typically ignore the relationship between training data knowledge and the model's inherent abilities, making it difficult to preserve prior knowledge. Second, conventional training objectives often fail to constrain inherent knowledge preservation, which can result in forgetting of previously learned skills. To address these issues, we propose a comprehensive solution that alleviates catastrophic forgetting from both the data and fine-tuning approach perspectives. On the data side, we construct a dataset of 5K instances that covers multiple reasoning tasks and incorporates metacognitive knowledge, making it more tolerant and effective for distillation into smaller models. We annotate the metacognitive knowledge required to solve each question and filter the data based on task knowledge and the model's inherent skills. On the training side, we introduce GDPO (Group Direction Preference Optimization), which is better suited for resource-limited scenarios and can efficiently approximate the performance of GRPO. Guided by the large model and by implicitly constraining the optimization path through a reference model, GDPO enables more effective knowledge transfer from the large model and constrains excessive parameter drift. Extensive experiments demonstrate that our approach significantly alleviates catastrophic forgetting and improves reasoning performance on smaller models. --- ### MediRound: Multi-Round Entity-Level Reasoning Segmentation in Medical Images Authors: Qinyue Tong, Ziqian Lu, Jun Liu, Rui Zuo, Zheming Lu, Yueming Jin Published: 2025-11-15 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2511.12110v5 Despite notable progress in text-guided medical image segmentation nowadays, these methods are limited to single-round dialogues and fail to support multi-round reasoning, which is important for medical education scenarios. In this work, we introduce Multi-Round Entity-Level Medical Reasoning Segmentation (MEMR-Seg), a new task that requires generating segmentation masks through multi-round queries with entity-level reasoning, helping learners progressively develop their understanding of medical knowledge. To support this task, we construct MR-MedSeg, a large-scale dataset of 177K multi-round medical segmentation dialogues, featuring entity-based reasoning across rounds. Furthermore, we propose MediRound, an effective baseline model designed for multi-round medical reasoning segmentation. To mitigate the inherent error propagation within the chain-like pipeline of multi-round segmentation, we introduce a lightweight yet effective Judgment & Correction Mechanism during model inference. Experimental results demonstrate that our method effectively addresses the MEMR-Seg task and outperforms conventional medical referring segmentation methods. The project is available at https://github.com/Edisonhimself/MediRound. --- ### Exploring Parameter-Efficient Fine-Tuning and Backtranslation for the WMT 25 General Translation Task Authors: Felipe Fujita, Hideyuki Takada Published: 2025-11-15 Categories: cs.CL arXiv: https://arxiv.org/abs/2511.12109v1 In this paper, we explore the effectiveness of combining fine-tuning and backtranslation on a small Japanese corpus for neural machine translation. Starting from a baseline English{\textrightarrow}Japanese model (COMET = 0.460), we first apply backtranslation (BT) using synthetic data generated from monolingual Japanese corpora, yielding a modest increase (COMET = 0.468). Next, we fine-tune (FT) the model on a genuine small parallel dataset drawn from diverse Japanese news and literary corpora, achieving a substantial jump to COMET = 0.589 when using Mistral 7B. Finally, we integrate both backtranslation and fine-tuning{ -- }first augmenting the small dataset with BT generated examples, then adapting via FT{ -- }which further boosts performance to COMET = 0.597. These results demonstrate that, even with limited training data, the synergistic use of backtranslation and targeted fine-tuning on Japanese corpora can significantly enhance translation quality, outperforming each technique in isolation. This approach offers a lightweight yet powerful strategy for improving low-resource language pairs. --- ### Fine-Grained DINO Tuning with Dual Supervision for Face Forgery Detection Authors: Tianxiang Zhang, Peipeng Yu, Zhihua Xia, Longchen Dai, Xiaoyu Zhou, Hui Gao Published: 2025-11-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.12107v1 The proliferation of sophisticated deepfakes poses significant threats to information integrity. While DINOv2 shows promise for detection, existing fine-tuning approaches treat it as generic binary classification, overlooking distinct artifacts inherent to different deepfake methods. To address this, we propose a DeepFake Fine-Grained Adapter (DFF-Adapter) for DINOv2. Our method incorporates lightweight multi-head LoRA modules into every transformer block, enabling efficient backbone adaptation. DFF-Adapter simultaneously addresses authenticity detection and fine-grained manipulation type classification, where classifying forgery methods enhances artifact sensitivity. We introduce a shared branch propagating fine-grained manipulation cues to the authenticity head. This enables multi-task cooperative optimization, explicitly enhancing authenticity discrimination with manipulation-specific knowledge. Utilizing only 3.5M trainable parameters, our parameter-efficient approach achieves detection accuracy comparable to or even surpassing that of current complex state-of-the-art methods. --- ### TEMPO: Global Temporal Building Density and Height Estimation from Satellite Imagery Authors: Tammy Glazer, Gilles Q. Hacheme, Akram Zaytar, Luana Marotti, Amy Michaels, Girmaw Abebe Tadesse, Kevin White, Rahul Dodhia, Andrew Zolli, Inbal Becker-Reshef, Juan M. Lavista Ferres, Caleb Robinson Published: 2025-11-15 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2511.12104v1 We present TEMPO, a global, temporally resolved dataset of building density and height derived from high-resolution satellite imagery using deep learning models. We pair building footprint and height data from existing datasets with quarterly PlanetScope basemap satellite images to train a multi-task deep learning model that predicts building density and building height at a 37.6-meter per pixel resolution. We apply this model to global PlanetScope basemaps from Q1 2018 through Q2 2025 to create global, temporal maps of building density and height. We validate these maps by comparing against existing building footprint datasets. Our estimates achieve an F1 score between 85% and 88% on different hand-labeled subsets, and are temporally stable, with a 0.96 five-year trend-consistency score. TEMPO captures quarterly changes in built settlements at a fraction of the computational cost of comparable approaches, unlocking large-scale monitoring of development patterns and climate impacts essential for global resilience and adaptation efforts. --- ### BdSL-SPOTER: A Transformer-Based Framework for Bengali Sign Language Recognition with Cultural Adaptation Authors: Sayad Ibna Azad, Md. Atiqur Rahman Published: 2025-11-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.12103v1 We introduce BdSL-SPOTER, a pose-based transformer framework for accurate and efficient recognition of Bengali Sign Language (BdSL). BdSL-SPOTER extends the SPOTER paradigm with cultural specific preprocessing and a compact four-layer transformer encoder featuring optimized learnable positional encodings, while employing curriculum learning to enhance generalization on limited data and accelerate convergence. On the BdSLW60 benchmark, it achieves 97.92% Top-1 validation accuracy, representing a 22.82% improvement over the Bi-LSTM baseline, all while keeping computational costs low. With its reduced number of parameters, lower FLOPs, and higher FPS, BdSL-SPOTER provides a practical framework for real-world accessibility applications and serves as a scalable model for other low-resource regional sign languages. --- ### Freeze, Share, Shrink: Rethinking the Action Backbone in Diffusion Policies Authors: Jian Zhou, Sihao Lin, Shuai Fu, Zerui Li, Gengze Zhou, Qi WU Published: 2025-11-15 Categories: cs.RO, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2511.12101v3 Many recent Vision-Language-Action models employ diffusion or flow-matching backbones with hundreds of millions of parameters for action generation. However, unlike image synthesis where the output spans millions of diverse pixels, a manipulation policy generates only short sequences of low-dimensional, physically correlated action values, a far simpler target that may not require such capacity. We confirm this intuition and show that, in modulation-conditioned diffusion policies, task adaptation can be routed entirely through the conditioning pathway, leaving a frozen, observation-free backbone that serves as a reusable trajectory prior. To establish this, we introduce a decoupled training recipe: a general-purpose action head is first pretrained on observation-free forward-kinematics data, then frozen while only the conditioning pathway is trained for downstream tasks. Using Diffusion Policy as a testbed, we show that on both MimicGen and LIBERO, a single frozen backbone shared across all tasks matches normally trained counterparts. In our ablations, this succeeds with modulation-based conditioning, while attention-based conditioning is embedded in the backbone's own weights and collapses once they are frozen. Ablations show the pretraining signal (joint positions, end-effector poses, or none) has little effect, while a randomly initialized backbone fails entirely, indicating that pretraining need only supply a general trajectory prior. Finally, a 5M-parameter MLP backbone matches or exceeds both the 244M U-Net and the transformer on these benchmarks, suggesting the action backbone is over-parameterized and that architectures inherited from image and language generation are a poor inductive-bias fit for the low-dimensional action target, with implications for action-backbone design in VLA models and other policies with an action backbone. --- ### Did Models Learn Sufficiently? Attribution-Guided Training via Subset-Selected Counterfactual Augmentation Authors: Yannan Chen, Ruoyu Chen, Wei Wang, Bin Zeng, Jinke Li, Shiming Liu, Qunli Zhang, Yaowei Wang, Xiaochun Cao Published: 2025-11-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.12100v3 Current visual models often make predictions based on a limited set of discriminative visual cues. As a result, they may become unreliable when the distribution shifts or when these cues are missing. Faithful attribution methods can reveal such problematic reliance through localized explanations, but they are typically used post hoc and are not fed back into the model. To address this limitation, we propose Subset-Selected Counterfactual Augmentation (SS-CA), a training strategy that masks decision-relevant regions to construct counterfactual samples and guide the model toward more robust decision boundaries. Specifically, we extend LIMA, a subset-selection-based faithful attribution method, to Counterfactual LIMA to identify regions whose removal shifts the model toward a competing class. SS-CA then selects near-boundary masks that reduce the logit gap while preserving the original semantics, and applies an adaptive counterfactual filling strategy to replace the masked regions without introducing external semantics. Feeding these counterfactual samples back into training encourages the model to exploit the remaining informative evidence and shifts the decision boundary toward a more robust one. Extensive experiments across five ImageNet variants show that SS-CA effectively improves ID accuracy, OOD generalization, and perturbation robustness, achieving gains of 5.70%/18.04% on ImageNet-1k/ImageNet-R with CLIP ViT/32b, 9.52%/11.33% on ImageNet-R/ImageNet-S on TinyImageNet-200 with ResNet-101, and about 4% under Gaussian Noise corruption. The code will be released soon. --- ### Adaptive Begin-of-Video Tokens for Autoregressive Video Diffusion Models Authors: Tianle Cheng, Zeyan Zhang, Kaifeng Gao, Jun Xiao Published: 2025-11-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.12099v1 Recent advancements in diffusion-based video generation have produced impressive and high-fidelity short videos. To extend these successes to generate coherent long videos, most video diffusion models (VDMs) generate videos in an autoregressive manner, i.e., generating subsequent frames conditioned on previous ones. There are generally two primary paradigms: chunk-based extension and stream denoising. The former directly concatenates previous clean frames as conditioning, suffering from denoising latency and error accumulation. The latter maintains the denoising sequence with monotonically increasing noise levels. In each denoising iteration, one clean frame is produced while a new pure noise is simultaneously appended, enabling live-stream sampling. However, it struggles with fragile consistency and poor motion dynamics. In this paper, we propose Adaptive Begin-of-Video Tokens (ada-BOV) for autoregressive VDMs. The BOV tokens are special learnable embeddings on VDMs. They adaptively absorb denoised preceding frames via an adaptive-layer-norm-like modulation. This design preserves the global consistency while allowing for flexible conditioning in dynamic scenarios. To ensure the quality of local dynamics essential in modulating BOV tokens, we further propose a refinement strategy for stream denoising. It decouples the sampling trajectory length from the attention window size constraint, leading to improved local guidance and overall imaging quality. We also propose a disturbance-augmented training noise schedule, which balances the convergence speed with model robustness for the stream denoising. Extensive experiments demonstrate that our method achieves compelling qualitative and quantitative results across multiple metrics. --- ### DINOv3-Guided Cross Fusion Framework for Semantic-aware CT generation from MRI and CBCT Authors: Xianhao Zhou, Jianghao Wu, Ku Zhao, Jinlong He, Huangxuan Zhao, Lei Chen, Shaoting Zhang, Guotai Wang Published: 2025-11-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.12098v1 Generating synthetic CT images from CBCT or MRI has a potential for efficient radiation dose planning and adaptive radiotherapy. However, existing CNN-based models lack global semantic understanding, while Transformers often overfit small medical datasets due to high model capacity and weak inductive bias. To address these limitations, we propose a DINOv3-Guided Cross Fusion (DGCF) framework that integrates a frozen self-supervised DINOv3 Transformer with a trainable CNN encoder-decoder. It hierarchically fuses global representation of Transformer and local features of CNN via a learnable cross fusion module, achieving balanced local appearance and contextual representation. Furthermore, we introduce a Multi-Level DINOv3 Perceptual (MLDP) loss that encourages semantic similarity between synthetic CT and the ground truth in DINOv3's feature space. Experiments on the SynthRAD2023 pelvic dataset demonstrate that DGCF achieved state-of-the-art performance in terms of MS-SSIM, PSNR and segmentation-based metrics on both MRI$\rightarrow$CT and CBCT$\rightarrow$CT translation tasks. To the best of our knowledge, this is the first work to employ DINOv3 representations for medical image translation, highlighting the potential of self-supervised Transformer guidance for semantic-aware CT synthesis. The code is available at https://github.com/HiLab-git/DGCF. --- ### Sparse by Rule: Probability-Based N:M Pruning for Spiking Neural Networks Authors: Shuhan Ye, Yi Yu, Qixin Zhang, Chenqi Kong, Qiangqiang Wu, Xudong Jiang, Dacheng Tao Published: 2025-11-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.12097v1 Brain-inspired Spiking neural networks (SNNs) promise energy-efficient intelligence via event-driven, sparse computation, but deeper architectures inflate parameters and computational cost, hindering their edge deployment. Recent progress in SNN pruning helps alleviate this burden, yet existing efforts fall into only two families: \emph{unstructured} pruning, which attains high sparsity but is difficult to accelerate on general hardware, and \emph{structured} pruning, which eases deployment but lack flexibility and often degrades accuracy at matched sparsity. In this work, we introduce \textbf{SpikeNM}, the first SNN-oriented \emph{semi-structured} \(N{:}M\) pruning framework that learns sparse SNNs \emph{from scratch}, enforcing \emph{at most \(N\)} non-zeros per \(M\)-weight block. To avoid the combinatorial space complexity \(\sum_{k=1}^{N}\binom{M}{k}\) growing exponentially with \(M\), SpikeNM adopts an \(M\)-way basis-logit parameterization with a differentiable top-\(k\) sampler, \emph{linearizing} per-block complexity to \(\mathcal O(M)\) and enabling more aggressive sparsification. Further inspired by neuroscience, we propose \emph{eligibility-inspired distillation} (EID), which converts temporally accumulated credits into block-wise soft targets to align mask probabilities with spiking dynamics, reducing sampling variance and stabilizing search under high sparsity. Experiments show that at \(2{:}4\) sparsity, SpikeNM maintains and even with gains across main-stream datasets, while yielding hardware-amenable patterns that complement intrinsic spike sparsity. --- ### Learning from Dense Events: Towards Fast Spiking Neural Networks Training via Event Dataset Distillation Authors: Shuhan Ye, Yi Yu, Qixin Zhang, Chenqi Kong, Qiangqiang Wu, Kun Wang, Xudong Jiang Published: 2025-11-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.12095v2 Event cameras sense brightness changes and output binary asynchronous event streams, attracting increasing attention. Their bio-inspired dynamics align well with spiking neural networks (SNNs), offering a promising energy-efficient alternative to conventional vision systems. However, SNNs remain costly to train due to temporal coding, which limits their practical deployment. To alleviate the high training cost of SNNs, we introduce \textbf{PACE} (Phase-Aligned Condensation for Events), the first dataset distillation framework to SNNs and event-based vision. PACE distills a large training dataset into a compact synthetic one that enables fast SNN training, which is achieved by two core modules: \textbf{ST-DSM} and \textbf{PEQ-N}. ST-DSM uses residual membrane potentials to densify spike-based features (SDR) and to perform fine-grained spatiotemporal matching of amplitude and phase (ST-SM), while PEQ-N provides a plug-and-play straight through probabilistic integer quantizer compatible with standard event-frame pipelines. Across DVS-Gesture, CIFAR10-DVS, and N-MNIST datasets, PACE outperforms existing coreset selection and dataset distillation baselines, with particularly strong gains on dynamic event streams and at low or moderate IPC. Specifically, on N-MNIST, it achieves \(84.4\%\) accuracy, about \(85\%\) of the full training set performance, while reducing training time by more than \(50\times\) and storage cost by \(6000\times\), yielding compact surrogates that enable minute-scale SNN training and efficient edge deployment. ---